检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

50,480 篇 会议
1,421 册 图书
1,042 篇 期刊文献
1 篇 学位论文

馆藏范围

52,941 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

31,809 篇 工学
- 24,802 篇 计算机科学与技术...
- 12,567 篇 软件工程
- 5,155 篇 光学工程
- 4,748 篇 电气工程
- 4,432 篇 信息与通信工程
- 4,257 篇 机械工程
- 3,950 篇 控制科学与工程
- 2,474 篇 生物工程
- 1,729 篇 生物医学工程（可授...
- 1,580 篇 仪器科学与技术
- 1,310 篇 电子科学与技术（可...
- 793 篇 化学工程与技术
- 697 篇 安全科学与工程
- 541 篇 交通运输工程
- 379 篇 建筑学
- 331 篇 土木工程
11,837 篇 理学
- 6,435 篇 物理学
- 5,405 篇 数学
- 2,761 篇 生物学
- 1,911 篇 统计学（可授理学、...
- 797 篇 化学
- 669 篇 系统科学
5,303 篇 医学
- 5,095 篇 临床医学
- 729 篇 基础医学(可授医学...
- 459 篇 药学(可授医学、理...
3,345 篇 管理学
- 1,951 篇 图书情报与档案管...
- 1,533 篇 管理科学与工程(可...
- 479 篇 工商管理
720 篇 艺术学
- 718 篇 设计学（可授艺术学...
428 篇 法学
- 401 篇 社会学
298 篇 农学
197 篇 教育学
163 篇 经济学
63 篇 文学
49 篇 军事学

主题

17,384 篇 computer vision
9,016 篇 pattern recognit...
4,195 篇 training
3,814 篇 feature extracti...
3,134 篇 cameras
2,870 篇 computational mo...
2,790 篇 image segmentati...
2,621 篇 visualization
2,573 篇 shape
2,533 篇 face recognition
2,171 篇 robustness
2,123 篇 computer science
1,972 篇 object detection
1,959 篇 computer archite...
1,878 篇 layout
1,852 篇 object recogniti...
1,802 篇 three-dimensiona...
1,725 篇 neural networks
1,708 篇 humans
1,691 篇 image recognitio...

机构

165 篇 univ chinese aca...
144 篇 tsinghua univers...
136 篇 national laborat...
107 篇 univ sci & techn...
104 篇 zhejiang univers...
100 篇 shanghai jiao to...
95 篇 microsoft resear...
94 篇 university of sc...
85 篇 zhejiang univ pe...
84 篇 shanghai ai lab ...
74 篇 school of comput...
69 篇 computer vision ...
68 篇 peking univ peop...
68 篇 chinese acad sci...
65 篇 chinese univ hon...
63 篇 institute of inf...
62 篇 google res mount...
61 篇 univ oxford oxfo...
59 篇 univ toronto on
57 篇 swiss fed inst t...

作者

91 篇 van gool luc
87 篇 umapada pal
76 篇 zhang lei
64 篇 lee seong-whan
50 篇 vittorio murino
42 篇 yang yi
34 篇 nassir navab
33 篇 li xin
33 篇 jie yang
32 篇 liu yang
31 篇 escalera sergio
31 篇 loy chen change
30 篇 ling haibin
30 篇 h. bischof
29 篇 zhou jie
29 篇 vasconcelos nuno
29 篇 jan-michael frah...
29 篇 hanqing lu
28 篇 blumenstein mich...
27 篇 jia yunde

语言

51,872 篇 英文
835 篇 其他
241 篇 中文
22 篇 土耳其文
5 篇 西班牙文
2 篇 日文
2 篇 葡萄牙文
2 篇 俄文

检索条件"任意字段=IEEE Conference on Computer Vision and Pattern Recognition"

共 52944 条记录，以下是4571-4580 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

PREDATOR: Registration of 3D Point Clouds with Low Overlap

PREDATOR: Registration of 3D Point Clouds with Low Overlap

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Huang, Shengyu Gojcic, Zan Usvyatsov, Mikhail Wieser, Andreas Schindler, Konrad Swiss Fed Inst Technol Zurich Switzerland

ISBN: (纸本)9781665445092

We introduce PREDATOR, a model for pairwise point-cloud registration with deep attention to the overlap region. Different from previous work, our model is specifically designed to handle (also) point-cloud pairs with low overlap. Its key novelty is an overlap-attention block for early information exchange between the latent encodings of the two point clouds. In this way the subsequent decoding of the latent representations into per-point features is conditioned on the respective other point cloud, and thus can predict which points are not only salient, but also lie in the overlap region between the two point clouds. The ability to focus on points that are relevant for matching greatly improves performance: PREDATOR raises the rate of successful registrations by more than 20% in the low-overlap scenario, and also sets a new state of the art for the 3DMatch benchmark with 89% registration recall.

关键词： Convolutional codes Solid modeling computer vision Three-dimensional displays Image matching computer architecture Encoding

来源：评论

学校读者我要写书评

暂无评论

Learning Asynchronous and Sparse Human-Object Interaction in Videos

Learning Asynchronous and Sparse Human-Object Interaction in...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Morais, Romero Vuong Le Venkatesh, Svetha Truyen Tran Deakin Univ Appl Artificial Intelligence Inst Geelong Vic Australia

ISBN: (纸本)9781665445092

Human activities can be learned from video. With effective modeling it is possible to discover not only the action labels but also the temporal structure of the activities, such as the progression of the sub-activities. Automatically recognizing such structure from raw video signal is a new capability that promises authentic modeling and successful recognition of human-object interactions. Toward this goal, we introduce Asynchronous-Sparse Interaction Graph Networks (ASSIGN), a recurrent graph network that is able to automatically detect the structure of interaction events associated with entities in a video scene. ASSIGN pioneers learning of autonomous behavior of video entities including their dynamic structure and their interaction with the coexisting neighbors. Entities' lives in our model are asynchronous to those of others therefore more flexible in adapting to complex scenarios. Their interactions are sparse in time hence more faithful to the true underlying nature and more robust in inference and learning. ASSIGN is tested on humanobject interaction recognition and shows superior performance in segmenting and labeling of human sub-activities and object affordances from raw videos. The native ability of ASSIGN in discovering temporal structure also eliminates the dependence on external segmentation that was previously mandatory for this task.

关键词： computer vision Analytical models Adaptation models Computational modeling Affordances Time series analysis pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Adversarial Robustness Across Representation Spaces

Adversarial Robustness Across Representation Spaces

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Awasthi, Pranjal Yu, George Ferng, Chun-Sung Tomkins, Andrew Juan, Da-Cheng Google Res Mountain View CA 94043 USA

ISBN: (纸本)9781665445092

Adversarial robustness corresponds to the susceptibility of deep neural networks to imperceptible perturbations made at test time. In the context of image tasks, many algorithms have been proposed to make neural networks robust to adversarial perturbations made to the input pixels. These perturbations are typically measured in an 4, norm. However, robustness often holds only for the specific attack used for training. In this work we extend the above setting to consider the problem of training of deep neural networks that can be made simultaneously robust to perturbations applied in multiple natural representations spaces. For the case of image data, examples include the standard pixel representation as well as the representation in the discrete cosine transform (DCT) basis. We design a theoretically sound algorithm with formal guarantees for the above problem. Furthermore, our guarantees also hold when the goal is to require robustness with respect to multiple 4, norm based attacks. We then derive an efficient practical implementation and demonstrate the effectiveness of our approach on standard datasets for image classification.(1)

关键词： Training Deep learning computer vision Perturbation methods Neural networks Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Wind Turbine Blade recognition Technology Based on 3D vision 4

A Wind Turbine Blade Recognition Technology Based on 3D Visi...

引用

4th International conference on computer Science and Blockchain, CCSB 2024

作者： Xu, Peiling Zhang, Xiaoyu School of Electrical Engineering Shanghai DianJi University Shanghai China

ISBN: (纸本)9798350356502

In order to solve the problem of wind turbine blade recognition, deep learning recognition methods are generally used. However, such algorithms require a large number of training samples and have high computational complexity. At present, there are also some algorithms that use the geometric structure of wind turbine blades for recognition. However, these algorithms do not take into account the perspective of drone cameras when shooting wind turbine blades, resulting in poor robustness of recognition algorithms based on the geometric structure between blades. In this paper, a coordinate transformation method based on point cloud data is proposed to solve this problem. The method first detects the edge information in the image from the acquired two-dimensional image coordinate system, and then transforms the edge information into a three-dimensional point cloud image. The RANSAC algorithm is used to obtain the plane normal of the wind turbine blade that is most likely to be in a plane in the edge information. The plane of the wind turbine blade is rotated using the spatial angle between the normal and the optical axis of the camera, so that the optical axis is perpendicular to the plane of the wind turbine blade, so that the geometric structure between the wind turbine blades after the coordinate transformation will not be distorted. The effectiveness of the proposed algorithm is verified by the recognition results under several different perspectives. Compared with the current mainstream algorithms based on the geometric structure of wind turbine blades, the proposed algorithm improves the recognition effect of wind turbine blades. © 2024 ieee.

关键词： Wind turbine blades

来源：评论

学校读者我要写书评

暂无评论

Google Tesseract: Optical Character recognition (OCR) on HDD/SSD Labels Using Machine vision 14

Google Tesseract: Optical Character Recognition (OCR) on HDD...

引用

14th International conference on computer and Automation Engineering (ICCAE)

作者： Estrada Bugayong, Vernon Flores Villaverde, Jocelyn Linsangan, Noel B. Mapua Univ Sch Grad Studies Manila Philippines Celest Elect Pte Ltd Woodlands Ave 5 Singapore Singapore Mapua Univ Sch Elect Elect & Comp Engn Manila Philippines

ISBN: (纸本)9781665483797

This paper is designed to have an optical character recognition system capable of interpreting captured images of hard disk drive and solid-state drive labels with high accuracy. Manual checking of the disk capacity size and part number found on the labels is time consuming, more prone to errors and utilizes more manpower. Automating the inspection through optical character recognition using image pre-processing and machine vision contributes to an easier inspection process, better management of records and faster cycle time. The images captured using a vision camera went through different stages of image pre-processing via OpenCV-Python and recognition through Google Tesseract. Different categorical variables including exposure time and location of texts in a captured image were used to determine and improve the overall recognition accuracy. By improving the lighting condition through the addition of light sources, the developed OCR system was able to achieve a character recognition accuracy of 99.375%.

关键词： Machine vision Tesseract Optical Character recognition Image Processing Python LabVIEW

来源：评论

学校读者我要写书评

暂无评论

2024 ieee 2nd International conference on Electrical, Automation and computer Engineering, ICEACE 2024

2024 IEEE 2nd International Conference on Electrical, Automa...

引用

2nd ieee International conference on Electrical, Automation and computer Engineering, ICEACE 2024

ISBN: (纸本)9798350368208

The proceedings contain 304 papers. The topics discussed include: parameter matching and regenerative braking energy recovery strategy for pure electric commercial vehicles;an optimized design of an electric vehicle wireless charging robotic arm;research on automatic classification and recognition system of works of art based on computer vision;research on energy-saving control strategy of residents' smart home;modeling designed for regenerative braking energy recovery of pure electric commercial vehicles;building facade design and optimization based on computer technology and improved genetic algorithm;application research of wireless sensor network in structural health monitoring of civil engineering;and design and application of control strategy for the ‘single forced draft fan, double induced draft fan, and double air preheater’ configuration of air and flue gas system in thermal power units.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal Understanding of Memes with Fair Explanations

Multimodal Understanding of Memes with Fair Explanations

引用

ieee computer Society conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Yang Zhong Bhiman Kumar Baghel Department of Computer Science University of Pittsburgh PA USA

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Digital Memes have been widely utilized in people’s daily lives over social media platforms. Composed of images and descriptive texts, memes are often distributed with the flair of sarcasm or humor, yet can also spread harmful content or biases from social and cultural factors. Aside from mainstream tasks such as meme generation and classification, generating explanations for memes has become more vital and poses challenges in avoiding propagating already embedded biases. Our work studied whether recent advanced vision Language Models (VL models) can fairly explain meme contents from different domains/topics, contributing to a unified benchmark for meme explanation. With the dataset, we semi-automatically and manually evaluate the quality of VL model-generated explanations, identifying the major categories of biases in meme explanations.

关键词： computer vision Social networking (online) conferences Computational modeling Benchmark testing pattern recognition Cultural differences

来源：评论

学校读者我要写书评

暂无评论

GLAVNet: Global-Local Audio-Visual Cues for Fine-Grained Material recognition

GLAVNet: Global-Local Audio-Visual Cues for Fine-Grained Mat...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Shi, Fengmin Guo, Jie Zhang, Haonan Yang, Shan Wang, Xiying Guo, Yanwen Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China IQIYI Intelligence Chongqing Heilongjiang Peoples R China

ISBN: (纸本)9781665445092

In this paper, we aim to recognize materials with combined use of auditory and visual perception. To this end, we construct a new dataset named GLAudio that consists of both the geometry of the object being struck and the sound captured from either modal sound synthesis (for virtual objects) or real measurements (for real objects). Besides global geometries, our dataset also takes local geometries around different hitpoints into consideration. This local information is less explored in existing datasets. We demonstrate that local geometry has a greater impact on the sound than the global geometry and offers more cues in material recognition. To extract features from different modalities and perform proper fusion, we propose a new deep neural network GLAVNet that comprises multiple branches and a well-designed fusion module. Once trained on GLAudio, our GLAVNet provides state-of-the-art performance on material identification and supports fine-grained material categorization.

关键词： Geometry Deep learning Visualization computer vision Feature extraction pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

The Translucent Patch: A Physical and Universal Attack on Object Detectors

The Translucent Patch: A Physical and Universal Attack on Ob...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Zolfi, Alon Kravchik, Moshe Elovici, Yuval Shabtai, Asaf Ben Gurion Univ Negev Dept Software & Informat Syst Engn Beer Sheva Israel

ISBN: (纸本)9781665445092

Physical adversarial attacks against object detectors have seen increasing success in recent years. However, these attacks require direct access to the object of interest in order to apply a physical patch. Furthermore, to hide multiple objects, an adversarial patch must be applied to each object. In this paper, we propose a contactless translucent physical patch containing a carefully constructed pattern, which is placed on the camera's lens, to fool state-of-the-art object detectors. The primary goal of our patch is to hide all instances of a selected target class. In addition, the optimization method used to construct the patch aims to ensure that the detection of other (untargeted) classes remains unharmed. Therefore, in our experiments, which are conducted on state-of-the-art object detection models used in autonomous driving, we study the effect of the patch on the detection of both the selected target class and the other classes. We show that our patch was able to prevent the detection of 42.27% of all stop sign instances while maintaining high (nearly 80%) detection of the other classes.

关键词： computer vision Face recognition Optimization methods Detectors Object detection Cameras Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Representative Batch Normalization with Feature Calibration

Representative Batch Normalization with Feature Calibration

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Gao, Shang-Hua Han, Qi Li, Duo Cheng, Ming-Ming Peng, Pai Nankai Univ CS TKLNDST Tianjin Peoples R China HKUST Hong Kong Peoples R China Tencent Shenzhen Peoples R China

ISBN: (纸本)9781665445092

Batch Normalization (BatchNorm) has become the default component in modern neural networks to stabilize training. In BatchNorm, centering and scaling operations, along with mean and variance statistics, are utilized for feature standardization over the batch dimension. The batch dependency of BatchNorm enables stable training and better representation of the network, while inevitably ignores the representation differences among instances. We propose to add a simple yet effective feature calibration scheme into the centering and scaling operations of BatchNorm, enhancing the instance-specific representations with the negligible computational cost. The centering calibration strengthens informative features and reduces noisy features. The scaling calibration restricts the feature intensity to form a more stable feature distribution. Our proposed variant of BatchNorm, namely Representative BatchNorm, can be plugged into existing methods to boost the performance of various tasks such as classification, detection, and segmentation.

关键词： Training computer vision Costs Neural networks Standardization Calibration pattern recognition

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 454 455 456 457 458 459 460 461 462 463 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：